Changdae Oh
@changdaeoh.bsky.social
CS PhD Student @ UW-Madison Distribution Shifts, Uncertainty Quantification, Multimodal, LLM Agents Prev: NAVER AI Lab, CMU, USeoul https://changdaeoh.github.io/
We tend to conflate "autonomy" with "reliability" in AI agents. But autonomy without trust is catastrophically dangerous. Our new paper formalizes UQ for LLM agents, proposes a new lens: agent uncertainty as a conditional uncertainty reduction process. 📄 huggingface.co/papers/2602....
Heading to #NeurIPS2024 to present our ‘Fair RAG’ paper at the #AFME2024 workshop! Let's talk about RAG, Information Retrieval, and Fairness. Honored that our paper was selected as one of the Top 5 Spotlight Papers! 🎉 Let’s connect and chat! Paper: arxiv.org/abs/2409.11598
Towards Fair RAG: On the Impact of Fair Ranking in Retrieval-Augmented Generation
Many language models now enhance their responses with retrieval capabilities, leading to the widespread adoption of retrieval-augmented generation (RAG) systems. However, despite retrieval being a cor...
arxiv.org